infosecn1nja

soc-triage-nemotron-bolt-e4b-lora-peft

README

License: openmdw-1.1

PEFT LoRA adapter (from MLX)

Converted from outputs/lora-pilot/adapters.safetensors (MLX) for vLLM/SGLang:

rank 8, alpha 160 (= MLX scale 20 x rank 8), targets: down_proj, gate_proj, o_proj, per_layer_input_gate, per_layer_projection, q_proj, up_proj
base: nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16

bash

vllm serve nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16 \  --enable-lora --max-lora-rank 8 \  --lora-modules soc-triage=infosecn1nja/soc-triage-nemotron-bolt-e4b-lora-peft

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

infosecn1nja

Model Tree

Base

nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16

Adapter

this model